End of training

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+base_model: BSC-LT/roberta-base-biomedical-clinical-es
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: roberta-base-biomedical-clinical-es-ner
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# roberta-base-biomedical-clinical-es-ner
+
+This model is a fine-tuned version of [BSC-LT/roberta-base-biomedical-clinical-es](https://huggingface.co/BSC-LT/roberta-base-biomedical-clinical-es) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3813
+- Precision: 0.8687
+- Recall: 0.8919
+- F1: 0.8801
+- Accuracy: 0.9374
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 280  | 0.3201          | 0.7961    | 0.8385 | 0.8167 | 0.9130   |
+| 0.5051        | 2.0   | 560  | 0.2833          | 0.8245    | 0.8770 | 0.8500 | 0.9282   |
+| 0.5051        | 3.0   | 840  | 0.2717          | 0.8459    | 0.8622 | 0.8540 | 0.9262   |
+| 0.1434        | 4.0   | 1120 | 0.2782          | 0.8477    | 0.8904 | 0.8685 | 0.9324   |
+| 0.1434        | 5.0   | 1400 | 0.3119          | 0.8525    | 0.8993 | 0.8753 | 0.9355   |
+| 0.0804        | 6.0   | 1680 | 0.3146          | 0.8639    | 0.8933 | 0.8784 | 0.9366   |
+| 0.0804        | 7.0   | 1960 | 0.3211          | 0.8637    | 0.8919 | 0.8776 | 0.9346   |
+| 0.0475        | 8.0   | 2240 | 0.3523          | 0.8707    | 0.8978 | 0.8840 | 0.9372   |
+| 0.0347        | 9.0   | 2520 | 0.3651          | 0.8434    | 0.8859 | 0.8642 | 0.9335   |
+| 0.0347        | 10.0  | 2800 | 0.3663          | 0.8706    | 0.8874 | 0.8789 | 0.9360   |
+| 0.0241        | 11.0  | 3080 | 0.3756          | 0.8680    | 0.8963 | 0.8819 | 0.9372   |
+| 0.0241        | 12.0  | 3360 | 0.3692          | 0.86      | 0.8919 | 0.8756 | 0.9369   |
+| 0.0201        | 13.0  | 3640 | 0.3782          | 0.8631    | 0.8874 | 0.8751 | 0.9360   |
+| 0.0201        | 14.0  | 3920 | 0.3820          | 0.8698    | 0.8904 | 0.8799 | 0.9374   |
+| 0.0172        | 15.0  | 4200 | 0.3813          | 0.8687    | 0.8919 | 0.8801 | 0.9374   |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "BSC-LT/roberta-base-biomedical-clinical-es",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-Anatomical_Entity",
+    "10": "I-Location",
+    "11": "B-Type_of_measure",
+    "12": "I-Type_of_measure",
+    "13": "B-Measure",
+    "14": "I-Measure",
+    "15": "B-Degree",
+    "16": "I-Degree",
+    "17": "B-ConditionalTemporal",
+    "18": "I-ConditionalTemporal",
+    "2": "I-Anatomical_Entity",
+    "3": "B-Finding",
+    "4": "I-Finding",
+    "5": "B-Uncertainty",
+    "6": "I-Uncertainty",
+    "7": "B-Negation",
+    "8": "I-Negation",
+    "9": "B-Location"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Anatomical_Entity": "1",
+    "B-ConditionalTemporal": "17",
+    "B-Degree": "15",
+    "B-Finding": "3",
+    "B-Location": "9",
+    "B-Measure": "13",
+    "B-Negation": "7",
+    "B-Type_of_measure": "11",
+    "B-Uncertainty": "5",
+    "I-Anatomical_Entity": "2",
+    "I-ConditionalTemporal": "18",
+    "I-Degree": "16",
+    "I-Finding": "4",
+    "I-Location": "10",
+    "I-Measure": "14",
+    "I-Negation": "8",
+    "I-Type_of_measure": "12",
+    "I-Uncertainty": "6",
+    "O": "0"
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a315038c7511011331579f85ee98dca9b0113e750b2f678ef57763ff0df4dd1f
+size 501632452

runs/Jun01_14-39-50_81a51b62e932/events.out.tfevents.1717252792.81a51b62e932.18149.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da5d3ebfd916dc65b3ced29e2b32ae7636c735de812622d9bc4e9d80657ac67e
+size 15084

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "51999": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaf661e65ffc36a8988e51c829cb0f3333dac356e349ef36a3fce51e971ae75b
+size 5176